Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52983
    Prev
    Next
    INDEX
    Explanations

    integers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensemble
    -0.08
     Memories
    -0.08
     gait
    -0.08
     contrad
    -0.08
     anime
    -0.08
     Fakten
    -0.08
     PBS
    -0.08
     swimsuit
    -0.08
    女孩
    -0.08
     adlı
    -0.08
    POSITIVE LOGITS
     gutter
    0.09
    арод
    0.08
     oxidation
    0.08
     DAO
    0.08
    xygen
    0.08
    twig
    0.08
    ąż
    0.07
    О
    0.07
    Ą
    0.07
     README
    0.07
    Activations Density 0.005%

    No Known Activations